Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598129
Dejene Boru Oljira, Karl-Johan Grinnemo, A. Brunström, J. Taheri
The next-generation networks (5G) aims to support services that demand strict requirements such as low-latency, high throughput, and high availability. Telecom operators have adopted Network Functions Virtualization (NFV) to virtualize the network functions and deploy at distributed cloud datacenters. Deploying virtual network functions (VNFs) close to the end-user can reduce Internet latency. However, network congestion in telco cloud datacenters can result in increased latency, low network utilization and a drop of throughput. The existing protocols are not capable of utilizing the multiple paths offered by datacenter topologies e.g., DCTCP; require a major architectural change and face deployment challenges e.g., NDP; or increase flow completion times of short flows e.g., MPTCP. To address this, we propose a multipath transport for telco cloud datacenters called coupled multipath datacenter TCP, MDTCP. MDTCP evolves MPTCP subflows to employ ECN signals to react to congestion before queue overflow, offering both reduced latency and higher network utilization. The evaluation of MDTCP with simulated traffic indicates comparable or lower flow completion times compared with DCTCP and NDP for most of the studied traffic scenarios. The simulation results imply that MDTCP could give better throughput for telco traffic and at the same time be as fair as MPTCP in datacenters.
{"title":"MDTCP: Towards a Practical Multipath Transport Protocol for Telco Cloud Datacenters","authors":"Dejene Boru Oljira, Karl-Johan Grinnemo, A. Brunström, J. Taheri","doi":"10.1109/NOF.2018.8598129","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598129","url":null,"abstract":"The next-generation networks (5G) aims to support services that demand strict requirements such as low-latency, high throughput, and high availability. Telecom operators have adopted Network Functions Virtualization (NFV) to virtualize the network functions and deploy at distributed cloud datacenters. Deploying virtual network functions (VNFs) close to the end-user can reduce Internet latency. However, network congestion in telco cloud datacenters can result in increased latency, low network utilization and a drop of throughput. The existing protocols are not capable of utilizing the multiple paths offered by datacenter topologies e.g., DCTCP; require a major architectural change and face deployment challenges e.g., NDP; or increase flow completion times of short flows e.g., MPTCP. To address this, we propose a multipath transport for telco cloud datacenters called coupled multipath datacenter TCP, MDTCP. MDTCP evolves MPTCP subflows to employ ECN signals to react to congestion before queue overflow, offering both reduced latency and higher network utilization. The evaluation of MDTCP with simulated traffic indicates comparable or lower flow completion times compared with DCTCP and NDP for most of the studied traffic scenarios. The simulation results imply that MDTCP could give better throughput for telco traffic and at the same time be as fair as MPTCP in datacenters.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116113033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8597858
S. Kukliński, Lechosław Tomaszewski, Krzysztof Kozlowski, Slawomir Pietrzyk
Network slicing is a technology that will soon influence the way in which new networking solutions will be designed and operated. The approach impacts the telco business ecosystem significantly. In this paper, we discuss two business models that are enabled by network slicing. One of them is applicable to a single infrastructure domain, whereas another concerns the involvement of multiple infrastructure and slice providers through the use of the brokering mechanism. We have also discussed the implementation of the business models. In that context, we have shown the shortcomings of the ETSI NFV MANO architecture in a multi-provider environment and proposed its modifications.
{"title":"Business models of network slicing","authors":"S. Kukliński, Lechosław Tomaszewski, Krzysztof Kozlowski, Slawomir Pietrzyk","doi":"10.1109/NOF.2018.8597858","DOIUrl":"https://doi.org/10.1109/NOF.2018.8597858","url":null,"abstract":"Network slicing is a technology that will soon influence the way in which new networking solutions will be designed and operated. The approach impacts the telco business ecosystem significantly. In this paper, we discuss two business models that are enabled by network slicing. One of them is applicable to a single infrastructure domain, whereas another concerns the involvement of multiple infrastructure and slice providers through the use of the brokering mechanism. We have also discussed the implementation of the business models. In that context, we have shown the shortcomings of the ETSI NFV MANO architecture in a multi-provider environment and proposed its modifications.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133885322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598136
L. Mauricio, M. Rubinstein, O. Duarte
Router Access Control Lists (ACLs) are a traditional way to filter traffic on cloud computing selectively. However, a large number of rules may be required, whereas the storage capacity of router Ternary Content Addressable Memories (TCAMs) is scarce and expensive. This paper proposes a Network Functions Virtualization (NFV)/Software-Defined Networking (SDN) security framework, named ACLFLOW. ACLFLOW (i) translates regular ACLs (source/destination IP, source/destination port, and protocol) into OpenFlow filtering rules; (ii) creates and manages large OpenFlow ACLs on distributed software switches, which act as security virtual network functions (named OpenFlow VNF-ACLs), to address the TCAM storage capacity problem; (iii) implements a proposed algorithm to dynamically prioritize the most popular rule to accelerate switching operations; and (iv) orchestrates and accelerates the deployment of NFV/SDN environments into production clouds. We have implemented a framework prototype into the Open Platform for NFV (OPNFV) and evaluated its performance using different tools and scenarios. Results show that OpenFlow VNF-ACL improves maximum throughput by up to 90%, its HTTP request rates are up to 50% better, and it reduces Round Trip Time (RTT) by 70% when its performance is compared with a stateless Iptables running in virtual machines. Moreover, the proposed algorithm dynamically improves HTTP request rate of flows with the highest traffic volume by 15% and reduces RTT by 25% when compared with ACLFLOW without prioritization.
{"title":"ACLFLOW: An NFV/SDN Security Framework for Provisioning and Managing Access Control Lists","authors":"L. Mauricio, M. Rubinstein, O. Duarte","doi":"10.1109/NOF.2018.8598136","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598136","url":null,"abstract":"Router Access Control Lists (ACLs) are a traditional way to filter traffic on cloud computing selectively. However, a large number of rules may be required, whereas the storage capacity of router Ternary Content Addressable Memories (TCAMs) is scarce and expensive. This paper proposes a Network Functions Virtualization (NFV)/Software-Defined Networking (SDN) security framework, named ACLFLOW. ACLFLOW (i) translates regular ACLs (source/destination IP, source/destination port, and protocol) into OpenFlow filtering rules; (ii) creates and manages large OpenFlow ACLs on distributed software switches, which act as security virtual network functions (named OpenFlow VNF-ACLs), to address the TCAM storage capacity problem; (iii) implements a proposed algorithm to dynamically prioritize the most popular rule to accelerate switching operations; and (iv) orchestrates and accelerates the deployment of NFV/SDN environments into production clouds. We have implemented a framework prototype into the Open Platform for NFV (OPNFV) and evaluated its performance using different tools and scenarios. Results show that OpenFlow VNF-ACL improves maximum throughput by up to 90%, its HTTP request rates are up to 50% better, and it reduces Round Trip Time (RTT) by 70% when its performance is compared with a stateless Iptables running in virtual machines. Moreover, the proposed algorithm dynamically improves HTTP request rate of flows with the highest traffic volume by 15% and reduces RTT by 25% when compared with ACLFLOW without prioritization.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134480232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598067
Krzysztof Mateusz Malarski, Alexander Victor Tietgen Bardram, Mikkel Delbo Larsen, Jakob Thrane, M.N. Petersen, L. Moeller, S. Ruepp
In this work we investigate signal strength and quality of Narrowband Internet of Things (NB-IoT) in a marine environment. In particular, we demonstrate the suitability of the NB-IoT technology as signal carrier for maritime applications, where water and boat masts can potentially affect the transmission.
{"title":"Demonstration of NB-IoT for Maritime Use Cases","authors":"Krzysztof Mateusz Malarski, Alexander Victor Tietgen Bardram, Mikkel Delbo Larsen, Jakob Thrane, M.N. Petersen, L. Moeller, S. Ruepp","doi":"10.1109/NOF.2018.8598067","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598067","url":null,"abstract":"In this work we investigate signal strength and quality of Narrowband Internet of Things (NB-IoT) in a marine environment. In particular, we demonstrate the suitability of the NB-IoT technology as signal carrier for maritime applications, where water and boat masts can potentially affect the transmission.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121788982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598127
Rumana Yasmin, Miikka Salminen, Ekaterina Gilman, J. Petäjäjärvi, Konstantin Mikhaylov, Minna Pakanen, A. Niemelä, J. Riekki, S. Pirttikangas, A. Pouttu
The internet of things (IoT) application domain is evolving continuously and is expected to bring digitalization making everything smart. This paper presents reference architecture for IoT system. Moreover, full implementation of such architecture is demonstrated with the IoT testbed deployed at the University of Oulu. Leveraging MQTT protocol, LoRaWAN is utilized as an IoT enabler technology for our platform, comprising a cloud server as well. In addition, a hybrid server is added to the platform to enable enhanced performance and functionality. To showcase the potential impacts of augmented reality (AR) based applications in an IoT infrastructure, we implemented and tested the maintenance support application. The implemented application visualizes environmental conditions and the sensor node itself as an augmented object on a mobile phone. A user study is carried out to discuss and showcase the potential impacts of using such a visualization approach.
{"title":"Combining IoT Deployment and Data Visualization: experiences within campus maintenance use-case","authors":"Rumana Yasmin, Miikka Salminen, Ekaterina Gilman, J. Petäjäjärvi, Konstantin Mikhaylov, Minna Pakanen, A. Niemelä, J. Riekki, S. Pirttikangas, A. Pouttu","doi":"10.1109/NOF.2018.8598127","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598127","url":null,"abstract":"The internet of things (IoT) application domain is evolving continuously and is expected to bring digitalization making everything smart. This paper presents reference architecture for IoT system. Moreover, full implementation of such architecture is demonstrated with the IoT testbed deployed at the University of Oulu. Leveraging MQTT protocol, LoRaWAN is utilized as an IoT enabler technology for our platform, comprising a cloud server as well. In addition, a hybrid server is added to the platform to enable enhanced performance and functionality. To showcase the potential impacts of augmented reality (AR) based applications in an IoT infrastructure, we implemented and tested the maintenance support application. The implemented application visualizes environmental conditions and the sensor node itself as an augmented object on a mobile phone. A user study is carried out to discuss and showcase the potential impacts of using such a visualization approach.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125142946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8597862
T. Ayar, L. Budzisz, B. Rathke
The idea to use multiple paths to transport TCP traffic seems very attractive due to its potential benefits it may offer for both redundancy and better utilization of available resources by load balancing. Fixed and mobile network providers employ frequently load-balancers that use multiple paths on either per-flow or per-destination level, but very seldom on per-packet level. Despite of the benefits of packet-level load balancing mechanisms (e.g., low computational complexity and high bandwidth utilization) network providers can’t use them mainly because of TCP packet reorderings that harm TCP performance. Emerging network architectures also support multiple paths, but they face with the same obstacle in balancing their load to multiple paths. Indeed, packet level load balancing research is paralyzed by the reordering vulnerability of TCP.A couple of TCP variants exist that deal with TCP packet reordering problem, but due to lack of end-to-end transparency they were not widely deployed and adopted. In this paper, we revisit TCP’s packet reorderings problem and present a transparent and light-weight algorithm, Out-of-Order Robustness for TCP with Transparent Acknowledgment (ACK) Intervention (ORTA), to deal with out-of-order deliveries.ORTA works as a transparent thin layer below TCP and hides harmful side-effects of packet-level load balancing. ORTA monitors all TCP flow packets and uses ACK traffic shaping, without any modifications to either TCP sender or receiver sides. Since it is transparent to TCP end-points, it can be easily deployed on TCP sender end-hosts (EHs), gateway (GW) routers, or access points (APs). ORTA opens a door for network providers to use per-packet load balancing.The proposed ORTA algorithm is implemented and tested in NS-2. The results show that ORTA can prevent TCP performance decrease when per-packet load balancing is used.
{"title":"A Transparent Reordering Robust TCP Proxy To Allow Per-Packet Load Balancing in Core Networks","authors":"T. Ayar, L. Budzisz, B. Rathke","doi":"10.1109/NOF.2018.8597862","DOIUrl":"https://doi.org/10.1109/NOF.2018.8597862","url":null,"abstract":"The idea to use multiple paths to transport TCP traffic seems very attractive due to its potential benefits it may offer for both redundancy and better utilization of available resources by load balancing. Fixed and mobile network providers employ frequently load-balancers that use multiple paths on either per-flow or per-destination level, but very seldom on per-packet level. Despite of the benefits of packet-level load balancing mechanisms (e.g., low computational complexity and high bandwidth utilization) network providers can’t use them mainly because of TCP packet reorderings that harm TCP performance. Emerging network architectures also support multiple paths, but they face with the same obstacle in balancing their load to multiple paths. Indeed, packet level load balancing research is paralyzed by the reordering vulnerability of TCP.A couple of TCP variants exist that deal with TCP packet reordering problem, but due to lack of end-to-end transparency they were not widely deployed and adopted. In this paper, we revisit TCP’s packet reorderings problem and present a transparent and light-weight algorithm, Out-of-Order Robustness for TCP with Transparent Acknowledgment (ACK) Intervention (ORTA), to deal with out-of-order deliveries.ORTA works as a transparent thin layer below TCP and hides harmful side-effects of packet-level load balancing. ORTA monitors all TCP flow packets and uses ACK traffic shaping, without any modifications to either TCP sender or receiver sides. Since it is transparent to TCP end-points, it can be easily deployed on TCP sender end-hosts (EHs), gateway (GW) routers, or access points (APs). ORTA opens a door for network providers to use per-packet load balancing.The proposed ORTA algorithm is implemented and tested in NS-2. The results show that ORTA can prevent TCP performance decrease when per-packet load balancing is used.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126594044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598130
Krzysztof Kozlowski, S. Kukliński, Lechosław Tomaszewski
Network slicing is a technology that will change the way in which future networks and services will be designed and operated. The approach impacts telco operators from the technical and business point of view. The technology is a subject of intensive research and standardization. The on-going work on network slicing has shown that many issues still have to be solved before the solution can be used by telco operators. Currently, the technology does not fulfill telco functional and performance-related requirements. In this paper, we describe the present status of network slicing and list the network slicing-related issues that still have to be solved. The list includes issues related to the scalability of slice management and orchestration, end-to-end slice orchestration, data plane and RAN slicing problems as well as business-oriented and legal issues.
{"title":"Open issues in network slicing","authors":"Krzysztof Kozlowski, S. Kukliński, Lechosław Tomaszewski","doi":"10.1109/NOF.2018.8598130","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598130","url":null,"abstract":"Network slicing is a technology that will change the way in which future networks and services will be designed and operated. The approach impacts telco operators from the technical and business point of view. The technology is a subject of intensive research and standardization. The on-going work on network slicing has shown that many issues still have to be solved before the solution can be used by telco operators. Currently, the technology does not fulfill telco functional and performance-related requirements. In this paper, we describe the present status of network slicing and list the network slicing-related issues that still have to be solved. The list includes issues related to the scalability of slice management and orchestration, end-to-end slice orchestration, data plane and RAN slicing problems as well as business-oriented and legal issues.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123704361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598138
Christian Dietz, Raphael Labaca Castro, Jessica Steinberger, Cezary W. Wilczak, Marcel Antzek, A. Sperotto, A. Pras
In recent years, emerging technologies such as the Internet of Things gain increasing interest in various communities. However, the majority of IoT devices have little or no protection at software and infrastructure levels and thus are also opening up new vulnerabilities that might be misused by cybercriminals to perform large-scale cyber attacks by means of IoT botnets. These kind of attacks lead to infrastructure and service outages and cause enormous financial loss, image and reputation damage. One approach to proactively block the spreading of such IoT botnets is to automatically scan for vulnerable IoT devices and isolate them from the Internet before they are compromised and also become part of the IoT botnet. The goal of this paper is to present an IoT botnet detection and isolation approach at the level of access routers that makes IoT devices more attack resilient. We show that our IoT botnet detection and isolation approach helps to prevent the compromise of IoT devices without the need to have in-depth technical administration knowledge, and hence make it viable for customers and end users.
{"title":"IoT-Botnet Detection and Isolation by Access Routers","authors":"Christian Dietz, Raphael Labaca Castro, Jessica Steinberger, Cezary W. Wilczak, Marcel Antzek, A. Sperotto, A. Pras","doi":"10.1109/NOF.2018.8598138","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598138","url":null,"abstract":"In recent years, emerging technologies such as the Internet of Things gain increasing interest in various communities. However, the majority of IoT devices have little or no protection at software and infrastructure levels and thus are also opening up new vulnerabilities that might be misused by cybercriminals to perform large-scale cyber attacks by means of IoT botnets. These kind of attacks lead to infrastructure and service outages and cause enormous financial loss, image and reputation damage. One approach to proactively block the spreading of such IoT botnets is to automatically scan for vulnerable IoT devices and isolate them from the Internet before they are compromised and also become part of the IoT botnet. The goal of this paper is to present an IoT botnet detection and isolation approach at the level of access routers that makes IoT devices more attack resilient. We show that our IoT botnet detection and isolation approach helps to prevent the compromise of IoT devices without the need to have in-depth technical administration knowledge, and hence make it viable for customers and end users.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122503901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598055
O. Salman, I. Elhajj, A. Chehab, A. Kayssi
In the network domain, there is a continuous ongoing evolution in the type of connected devices and the nature of developed applications. This presents the network with varying Quality of Service (QoS) and security requirements. Consequently, there is a need to classify Internet traffic to facilitate its management. Thus, a granular classification based on needs is required, one which relates better to the network requirements of the traffic. In this paper, we apply deep learning to classify traffic requiring different QoS and security policies. We propose a multi-level classification framework applying a new data representation method. A comparison between the proposed data representation method and a previous method is presented. The implementation results show that the proposed data representation model outperforms the previous one and promises to permit the classification of the traffic at different granularity. Recording up to 95% accuracy using only the size, interarrival time, direction, transport protocol of the first 16 packets of each flow, our method can be employed in an online classification platform.
{"title":"A Multi-level Internet Traffic Classifier Using Deep Learning","authors":"O. Salman, I. Elhajj, A. Chehab, A. Kayssi","doi":"10.1109/NOF.2018.8598055","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598055","url":null,"abstract":"In the network domain, there is a continuous ongoing evolution in the type of connected devices and the nature of developed applications. This presents the network with varying Quality of Service (QoS) and security requirements. Consequently, there is a need to classify Internet traffic to facilitate its management. Thus, a granular classification based on needs is required, one which relates better to the network requirements of the traffic. In this paper, we apply deep learning to classify traffic requiring different QoS and security policies. We propose a multi-level classification framework applying a new data representation method. A comparison between the proposed data representation method and a previous method is presented. The implementation results show that the proposed data representation model outperforms the previous one and promises to permit the classification of the traffic at different granularity. Recording up to 95% accuracy using only the size, interarrival time, direction, transport protocol of the first 16 packets of each flow, our method can be employed in an online classification platform.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122836450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-11-01DOI: 10.1109/NOF.2018.8598123
J. Galán-Jiménez, L. Chiaraviglio, L. Amorosi, N. Blefari-Melazzi
Nowadays, at least two billion people are experiencing a complete lack of cellular coverage. Since the lack of cellular connectivity is mostly experienced in rural zones, it is of mandatory importance to design solutions to manage cellular architectures tailored to such zones. To this aim, we consider a new cellular 5G architecture, where the Base Stations (BSs) are carried by Unmanned Aerial Vehicles (UAVs). Specifically, we focus on the problem of planning the missions of the UAV-based BSs over the territory, with the goal of minimizing the energy consumed for moving the UAVs. After introducing the considered framework, which is based on a multi-period graph defined over a set of places and a set of Time Slots (TSs), we derive a simple algorithm, called GAUP, to solve the considered problem in a reasonable amount of time. Our results, obtained over a simple - yet representative - scenario, reveals that GAUP is able to efficiently manage the energy for moving the UAVs, while guaranteeing relatively low computation times.
{"title":"Multi-Period Mission Planning of UAVs for 5G Coverage in Rural Areas: a Heuristic Approach","authors":"J. Galán-Jiménez, L. Chiaraviglio, L. Amorosi, N. Blefari-Melazzi","doi":"10.1109/NOF.2018.8598123","DOIUrl":"https://doi.org/10.1109/NOF.2018.8598123","url":null,"abstract":"Nowadays, at least two billion people are experiencing a complete lack of cellular coverage. Since the lack of cellular connectivity is mostly experienced in rural zones, it is of mandatory importance to design solutions to manage cellular architectures tailored to such zones. To this aim, we consider a new cellular 5G architecture, where the Base Stations (BSs) are carried by Unmanned Aerial Vehicles (UAVs). Specifically, we focus on the problem of planning the missions of the UAV-based BSs over the territory, with the goal of minimizing the energy consumed for moving the UAVs. After introducing the considered framework, which is based on a multi-period graph defined over a set of places and a set of Time Slots (TSs), we derive a simple algorithm, called GAUP, to solve the considered problem in a reasonable amount of time. Our results, obtained over a simple - yet representative - scenario, reveals that GAUP is able to efficiently manage the energy for moving the UAVs, while guaranteeing relatively low computation times.","PeriodicalId":319444,"journal":{"name":"2018 9th International Conference on the Network of the Future (NOF)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128824295","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：